An efficient deepfake video detection using robust deep learning.

The creation and manipulation of synthetic images have evolved rapidly, causing serious concerns about their effects on society. Although there have been various attempts to identify deep fake videos, these approaches are not universal. Identifying these misleading deepfakes is the first step in preventing them from spreading on social media sites. We introduce a unique deep-learning technique to identify fraudulent clips. Most deepfake identifiers currently focus on identifying face exchange, lip synchronous, expression modification, puppeteers, and other factors. However, exploring a consistent basis for all forms of fake videos and images in real-time forensics is challenging. We propose a hybrid technique that takes input from videos of successive targeted frames, then feeds these frames to the ResNet-Swish-BiLSTM, an optimized convolutional BiLSTM-based residual network for training and classification. This proposed method helps identify artifacts in deepfake images that do not seem real. To assess the robustness of our proposed model, we used the open deepfake detection challenge dataset (DFDC) and Face Forensics deepfake collections (FF++). We achieved 96.23% accuracy when using the FF++ digital record. In contrast, we attained 78.33% accuracy using the aggregated records from FF++ and DFDC. We performed extensive experiments and believe that our proposed method provides more significant results than existing techniques.

A framework for brain tumor detection based on segmentation and features fusion using MRI images.

Irregular growth of cells in the skull is recognized as a brain tumor that can have two types such as benign and malignant. There exist various methods which are used by oncologists to assess the existence of brain tumors such as blood tests or visual assessments. Moreover, the noninvasive magnetic resonance imaging (MRI) technique without ionizing radiation has been commonly utilized for diagnosis. However, the segmentation in 3-dimensional MRI is time-consuming and the outcomes mainly depend on the operator's experience. Therefore, a novel and robust automated brain tumor detector has been suggested based on segmentation and fusion of features. To improve the localization results, we pre-processed the images using Gaussian Filter (GF), and SynthStrip: a tool for brain skull stripping. We utilized two known benchmarks for training and testing i.e., Figshare and Harvard. The proposed methodology attained 99.8% accuracy, 99.3% recall, 99.4% precision, 99.5% F1 score, and 0.989 AUC. We performed the comparative analysis of our approach with prevailing DL, classical, and segmentation-based approaches. Additionally, we also performed the cross-validation using Harvard dataset attaining 99.3% identification accuracy. The outcomes exhibit that our approach offers significant outcomes than existing methods and outperforms them.

A Novel Hybrid Approach Based on Deep CNN Features to Detect Knee Osteoarthritis.

In the recent era, various diseases have severely affected the lifestyle of individuals, especially adults. Among these, bone diseases, including Knee Osteoarthritis (KOA), have a great impact on quality of life. KOA is a knee joint problem mainly produced due to decreased Articular Cartilage between femur and tibia bones, producing severe joint pain, effusion, joint movement constraints and gait anomalies. To address these issues, this study presents a novel KOA detection at early stages using deep learning-based feature extraction and classification. Firstly, the input X-ray images are preprocessed, and then the Region of Interest (ROI) is extracted through segmentation. Secondly, features are extracted from preprocessed X-ray images containing knee joint space width using hybrid feature descriptors such as Convolutional Neural Network (CNN) through Local Binary Patterns (LBP) and CNN using Histogram of oriented gradient (HOG). Low-level features are computed by HOG, while texture features are computed employing the LBP descriptor. Lastly, multi-class classifiers, that is, Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), are used for the classification of KOA according to the Kellgren-Lawrence (KL) system. The Kellgren-Lawrence system consists of Grade I, Grade II, Grade III, and Grade IV. Experimental evaluation is performed on various combinations of the proposed framework. The experimental results show that the HOG features descriptor provides approximately 97% accuracy for the early detection and classification of KOA for all four grades of KL.

Insight into chitosan/zeolite-A nanocomposite as an advanced carrier for levofloxacin and its anti-inflammatory properties; loading, release, and anti-inflammatory studies.

Chitosan/zeolite-A nanocomposite (CH/ZA) was synthesized as a potential carrier for levofloxacin (LVOX) of enhanced technical properties. The CH/ZA composite displayed enhanced loading capacity (425 mg/g) as compared to chitosan (188.8 mg/g) and zeolite-A (234.6 mg/g). The loading behavior follows Pseudo-Second-order and Langmuir as kinetic and isotherm models. The equilibrium studies, Gaussian energy (8.15 KJ/mol), and thermodynamic parameters demonstrate homogenous and monolayer loading by complex chemical and physical reactions that are of spontaneous and exothermic nature. The CH/ZA composite is of slow and continuous release profile (200h) with 94.3% as the maximum release percentage. The release reactions are of non-Fickian behavior involving both diffusion and erosion mechanisms. The loading of LVOX into CH/ZA induced its anti-inflammatory effect against the cytokine production (IL-6 and IL-8) within the human bronchial epithelia cells (NL20). The cytotoxicity studies on the normal cells demonstrated a high safety value for the composite.

Sonocogreen Decoration of Clinoptilolite by CaO Nanorods as Ecofriendly Catalysts in the Transesterification of Castor Oil into Biodiesel; Response Surface Studies.

A CaO/clinoptilolite green nanocomposite (CaO/Clino) was synthesized by a green modification technique using calcium nitrate and green tea extract. The CaO/Clino nanocomposite promises a total basicity of 4.82 mmol OH/g, surface area of 252.4 m2/g, and ion exchange capacity of 134.3 mequiv/100 g, which qualifies the product as an effective catalyst in the transesterification of castor oil. The transesterification performance of the CaO/Clino catalyst was addressed statistically based on the response surface methodology and central composite rotatable design, considering the essential experimental parameters. Based on the interaction effect between the studied variables, the CaO/Clino catalyst can achieve an experimental biodiesel yield of 93.8% after 2.5 h at 120 °C with 3.5 wt % catalyst loading and 15:1 ethanol/castor oil molar ratio. The optimization function of the design suggested enhancement in the performance of the CaO/Clino catalyst to achieve a yield of 95.4% if the test time interval increased to 2.65 h and the ethanol content increased to 16:1 as a molar ratio to castor oil. The produced biodiesel over CaO/ClinO has acceptable technical qualifications according to the international requirements (EN 14214 and ASTM D-6751). The synthetic green CaO/Clino nanocomposite has better recyclability as a heterogeneous catalyst and higher activity than some investigated catalysts in literature.

Instantaneous Adsorption of Synthetic Dyes from an Aqueous Environment Using Kaolinite Nanotubes: Equilibrium and Thermodynamic Studies.

Innovative kaolinite nanotubes (KNTs) are synthesized utilizing a simple technique involving a sonication-induced exfoliation process, followed by chemical scrolling reactions. The KNTs as a material have high reactivity and promising surface area to be used in the purification of water from cationic dyes (safranin (SF) and malachite green (MG)) and anionic dyes (methyl orange (MO) and Congo red (CR)). The kinetic studies of the four dyes SF, MG, CR, and MO show an equilibration time interval of 240 min. The SF, MG, CR, and MO dyes' uptake reactions are in agreement with the kinetic behavior of the pseudo-first-order model and the equilibrium properties of the Langmuir model. Such modeling results, in addition to the Gaussian energies from the Dubinin-Radushkevich (D-R) model (SF (1.01 kJ/mol), MG (1.08 kJ/mol), CR (1.11 kJ/mol), and MO (1.65 kJ/mol)), hypothesize monolayer adsorption of the four dyes by physical reactions. The KNTs show theoretical q max values of 431.6, 489.9, 626.2, and 675.5 (mg/g) for SF, MG, CR, and MO, respectively. The thermodynamic examination of SF, MG, CR, and MO adsorption reactions using KNTs verifies their adsorption by exothermic and spontaneous reactions. The KNT adsorbents achieve promising adsorption results in the presence of different coexisting ions and show significant recyclability properties. Therefore, the production of KNTs from kaolinite shows a strong effect on inducing the textural, physicochemical, and adsorption properties of clay layers as well as their affinity for different species of synthetic dyes.

Insight into chitosan/mesoporous silica nanocomposites as eco-friendly adsorbent for enhanced retention of U (VI) and Sr (II) from aqueous solutions and real water.

The chitosan chains were integrated with MCM-48 mesoporous silica in an eco-friendly composite (CH/MCM-48) of enhanced adsorption capacity. The prepared CH/MCM-48 composite was applied in systematic retention of U (VI) as well as Sr (II) ions from water as the commonly detected radioactive pollutants. It displayed promising retention capacities of 261.3 mg/g and 328.6 mg/g for U (VI) and Sr (II) considering the equilibrium time interval that was identified after 420 min. The composite showed the kinetic behavior of the Pseudo-First order model and the isotherm properties of the Langmuir assumption. The thermodynamic assessment of the reactions validated the retention of both U (VI) and Sr (II) ions by spontaneous, favorable, and exothermic reactions. Based on the theoretical values of entropy (-5.94 kJ mol-1 (U (VI)) and -2.93 kJ mol-1 (Sr (II))), Gibbs free energy (less than 20 kJ mol-1), and Gaussian energy (5.77 kJ mol-1 (U (VI)) and 4.56 kJ mol-1 (Sr (II))) the uptake processes are related to physical adsorption reactions. The CH/MCM-48 composite is of significant recyclability and showed considerable affinities for the studied radioactive ions even in the presence of other metal ions (Cd (II), Pb (II), Zn (II), and Co (II)).

Insights into the green doping of clinoptilolite with Na+ ions (Na+/Clino) as a nanocatalyst in the conversion of palm oil into biodiesel; optimization and mechanism.

The critical demand for eco-friendly, renewable, and safe energy resources is an essential issue encountered in the contemporary world. The catalytic transesterification of plant oils into biodiesel was assessed as promising a technique for providing new forms of clean and safe fuel. Natural clinoptilolite was doped with Na+ ions by green chemical reactions between sodium nitrite and green tea extract, producing a novel modified structure (Na+/Clino). The Na+/Clino product had an enhanced total basicity (6.41 mmol OH/g), ion exchange capacity (387 meq/100 g), and surface area (312.7 m2 g-1), which qualified it to be used as a potential basic catalyst for the transesterification of palm oil. Transesterification tests were statistically assessed using a response surface methodology and a central composite design. Considering the effect of how the significant factors interact with each other, the synthetic Na+/Clino achieved a 96.4% experimental biodiesel yield after 70 min at 100 °C in the presence of 2.75 wt% catalyst loading and a 12.5:1 methanol-to-palm-oil ratio. Based on the optimization function of the statistical model, the performance of Na+/Clino can theoretically be enhanced to increase the yield to 98.2% by expanding the test time to 85 min and the loading value to 3 wt%. The product yielded by the Na+/ClinO process is of adequate technical properties, considering the international levels for standard biodiesel (EN 14214 and ASTM D-6751). Finally, the prepared green Na+ doped clinoptilolite had excellent recyclability as a heterogeneous basic catalyst and displayed higher efficiency than several species of previously studied heterogeneous and homogenous catalysts.

Insight into carbohydrate polymers (chitosan and 2- hydroxyethyl methacrylate/methyl methacrylate) intercalated bentonite-based nanocomposites as multifunctional and environmental adsorbents for methyl parathion pesticide.

Two-hybrid products of bentonite intercalated carbohydrate polymers (chitosan (BE.P.CH) and 2- hydroxyethyl methacrylate/methyl methacrylate copolymer (BE/P.HEMA/MMA)) were synthesized as enhanced adsorbents for methyl parathion pesticide (MPP). The intercalation processes induced the affinity and the capacity of bentonite achieving the best value at pH 8. The maximum MPP adsorption capacities of BE (287.3 mg/g), BE/P.CH (634.5 mg/g), and BE/P.HEMA-MMA (868.5 mg/g) obtained after 300 min, 240 min, and 360 min, respectively. The kinetic properties of BE follow the Pseudo-second order behavior (R2 = 0.93) while BE/P.CH and BE/P.HEMA-MMA are of Pseudo-First order behavior (R2 > 0.92). Based on the equilibrium studies, the three products are of Freundlich isotherm behavior (R2 > 0.9) and the uptake is of multilayer forms on heterogeneous surfaces. The Gaussian energies (>8 KJ/mol), Gibbs free energies (>20 to <40 KJ/mol), and enthalpies (>40 to <80 KJ/mol) give an indication about adsorption mechanism involved chemical and physical reactions. The thermodynamics of MPP uptake reactions by the three products are of endothermic and spontaneous behaviors. The MPP uptake in the presence of NH+4, PO4-3, Mn+2, and Pb+2 competitive ions reflects enhancement in the affinity of BE after the integration between it and the selected polymers.

Enhancing the removal of organic and inorganic selenium ions using an exfoliated kaolinite/cellulose fibres nanocomposite.

Exfoliated kaolinite sheets/cellulose fibres nanocomposite (EXK/CF) was synthesised as a novel hybrid of materials of enhanced surface area and adsorption capacities for inorganic-selenate [Se(VI)] and selenite [Se(IV)]-and organic selenium pollutants-selenomethionine (SeMt). The adsorption reactions of the addressed selenium forms followed pseudo-first-order as a kinetic model and Langmuir as an isotherm model. The fitting results and the calculated Gaussian energies-Se (VI) at 2.0 KJ/mol, Se (IV) at 2.2 KJ/mol, and SeMt at 1.7 KJ/mol-suggested physisorption uptake in a monolayer and homogeneous form. The theoretical maximum selenium uptake capacity (qmax) for Se (VI), Se (IV), and SeMt was 137.5 mg/g, 161.4 mg/g, and 95.4 mg/g, respectively. The thermodynamic investigation verified spontaneous and exothermic properties of the selenium uptake reactions by the EXK/CF composite.

Instantaneous oxidation of levofloxacin as toxic pharmaceutical residuals in water using clay nanotubes decorated by ZnO (ZnO/KNTs) as a novel photocatalyst under visible light source.

Kaolinite nanotubes were synthesized by a simple scrolling process and decorated by ZnO nanoparticles as a novel nanocomposite (ZnO/KNTs). The synthetic ZnO/KNTs composite was characterized as an effective photocatalyst in the oxidation of levofloxacin pharmaceutical residuals in the water resources. The composite displays a surface area of 95.4 m2/g, average pore diameter of 5.8 nm, and bandgap energy of 2.12 eV. It is of high catalytic activity in the oxidation of levofloxacin in the presence of visible light source. The complete oxidation for 10 mg/L of levofloxacin was recognized after 55 min, 45 min, and 30 min with applying 30 mg, 40 mg, and 50 mg of ZnO/KNTs as catalyst dosage, respectively. Additionally, it achieved complete oxidation for 20 mg/L and 30 mg/L of levofloxacin after 45 min and 75 min, respectively using 50 mg as catalyst dosage. The degradation efficiency was confirmed by detecting the residual TOC after the treatment tests and the formed intermediate compounds were identified to suggest the degradation pathways. In addition to the oxidation pathway, the mechanism was evaluated based on the active trapping tests that proved the dominance of hydroxyl radicals as the essential active species. Finally, the ZnO/KNTs composite is of promising recyclability properties and achieved better results than several studied photocatalysts in literature.

Insight into the Loading and Release Properties of MCM-48/Biopolymer Composites as Carriers for 5-Fluorouracil: Equilibrium Modeling and Pharmacokinetic Studies.

The effect of the integration between MCM-48 and some biopolymers (starch, chitosan, and ß-cyclodextrin) on enhancing the pharmaceutical properties of MCM-48 as advanced carriers for the 5-fluorouracil drug was studied considering the loading capacities and the release profiles. The prepared carriers are MCM-48/chitosan (MCM/CH), MCM-48/starch composite (MCM/ST), and MCM-48/ß-Cyclodextrin (MCM/CD). They emphasized excellent 5-Fu loading capacities of 141.2 mg/g (MCM-48), 156.6 mg/g (MCM/ST), 191 mg/g (MCM/CH), and 170 mg/g (MCM/CD), reflecting significant enhancement in the loading capacities. The kinetic and equilibrium investigation suggested physisorption loading of 5-Fu drug in a monolayer form for MCM-48, MCM/ST, and MCM/CH (Langmuir) and in a multilayer form for MCM/CD (Freundlich). This was supported by the estimated adsorption energies (0.23 kJ/mol (MCM-48), 0.26 kJ/mol (MCM/ST), 0.3 kJ/mol (MCM/CH), and 0.75 kJ/mol (MCM/CD)) and the thermodynamic parameters of free energy and enthalpy. The obtained release profiles for 80 h reflected significant controlling for the releasing behavior of MCM/48 on integrating its structure by adjusting the type of the selected polymer and its ratio. The pharmacokinetic modeling and the diffusion exponent from the Korsmeyer-Peppas model suggested non-Fickian transport behavior (a combination of erosion and diffusion releasing mechanism) for MCM/ST, MCM/CH, and MCM/CD and Fickian diffusion behavior (diffusion releasing mechanism) for MCM-48.

Biogenic Gold Nanoparticles as Potent Antibacterial and Antibiofilm Nano-Antibiotics against Pseudomonas aeruginosa.

Abstract: Plant-based synthesis of eco-friendly nanoparticles has widespread applications in many fields, including medicine. Biofilm-a shield for pathogenic microorganisms-once formed, is difficult to destroy with antibiotics, making the pathogen resistant. Here, we synthesized gold nanoparticles (AuNPs) using the stem of an Ayurvedic medicinal plant, Tinospora cordifolia, and studied the action of AuNPs against Pseudomonas aeruginosa PAO1 biofilm. The synthesized AuNPs were characterized by techniques such as ultraviolet-visible spectroscopy, Fourier-transform infrared (FTIR) spectroscopy, energy-dispersive X-ray diffraction, X-ray diffraction, scanning electron microscopy (SEM), and transmission electron microscopy. The AuNPs were spherically shaped with an average size of 16.1 nm. Further, the subminimum inhibitory concentrations (MICs) of AuNPs (50, 100, and 150 µg/mL) greatly affected the biofilm-forming ability of P. aeruginosa, as observed by crystal violet assay and SEM, which showed a decrease in the number of biofilm-forming cells with increasing AuNP concentration. This was further justified by confocal laser scanning microscopy (CLSM), which showed irregularities in the structure of the biofilm at the sub-MIC of AuNPs. Further, the interaction of AuNPs with PAO1 at the highest sub-MIC (150 µg/mL) showed the internalization of the nanoparticles, probably affecting the tendency of PAO1 to colonize on the surface of the nanoparticles. This study suggests that green-synthesized AuNPs can be used as effective nano-antibiotics against biofilm-related infections caused by P. aeruginosa.

Preparation of letrozole dispersed pHEMA/AAm-g-LDPE drug release system: In-vitro release kinetics for the treatment of endometriosis.

This paper focuses on the development of a drug delivery system for systemically controlled release of a poorly soluble drug, letrozole. The work meticulously describes the preparation and characterizations of 2-hydroxyethyl methacrylate (HEMA) polymerization onto hydrophilic acrylamide grafted low-density polyethylene (AAm-g-LDPE) surface for targeted drug release system. The surface morphology and thickness measurement of coated pHEMA layer were measured using scanning electron microscopy (SEM). The swelling study was done in deionized (DI) water and simulated uterine fluid (SUF, pH = 7.6). In vitro release of letrozole from the system was performed in SUF. Further, the release kinetics of letrozole from the system was studied using different mathematical models. The results, suggest that the rate of drug release can be altered by varying the concentrations of cross-linker in pHEMA. The optimized sample released 72% drug at the end of 72 h of measurement.